Multi-Expert Routing for Multi-Domain Low-Resource OCR: A Manchu Case Study
Historical Manchu OCR must accommodate various visually distinct writing styles, including regular script, running script, and the semi-cursive chancery hand used in palace memorials, despite limited labeled data. We study a multi-expert system that reuses checkpoints from an iterative fine-tuning process as domain specialists and uses a lightweight page-level image classifier to dispatch pages by visual style. When the checkpoint pool lacks a suitable specialist, we train an additional expert for that domain. On three frozen test sets, the routed system matches the selected specialist for eac
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 50%Find the best open-source OCR models in one place at Papers with Code [P] →
- PossiblePossibly related (embedding) · 49%Pair Nova 2 Lite with Claude for cost-optimized document processing →
- PossiblePossibly related (embedding) · 45%TurboOCR v3 — high-speed document OCR server (C++/CUDA), ~520 img/s on RTX 5090 →
- LinkedLinked via arxiv author · 85%Zhan Chen →
“Multi-Expert Routing for Multi-Domain Low-Resource OCR: A Manchu Case Study”
- LinkedLinked via arxiv author · 85%Jiqiao Ma →
“Multi-Expert Routing for Multi-Domain Low-Resource OCR: A Manchu Case Study”
- LinkedLinked via arxiv author · 85%Chih-wen Kuo →
“Multi-Expert Routing for Multi-Domain Low-Resource OCR: A Manchu Case Study”